I have the following code to get a look from Looker through an API. I stored the api in a .ini. All of that works, but now I want to get the data from this look as Dataframe in python, so that I can use the data for further analysis. How can i do that? I used this code, but that only saves it to png. I can't find a way to create a dataframe from this, as I want the data itself and not just the outcome image.
import sys
import textwrap
import time
import looker_sdk
from looker_sdk import models
sdk = looker_sdk.init40("/Name.ini")
def get_look(title: str) -> models.Look:
title = title.lower()
look = next(iter(sdk.search_looks(title=title)), None)
if not look:
raise Exception(f"look '{title}' was not found")
return look
def download_look(look: models.Look, result_format: str, width: int, height: int):
"""Download specified look as png/jpg"""
id = int(look.id)
task = sdk.create_look_render_task(id, result_format, width, height,)
if not (task and task.id):
raise sdk.RenderTaskError(
f"Could not create a render task for '{look.title}'"
)
# poll the render task until it completes
elapsed = 0.0
delay = 0.5 # wait .5 seconds
while True:
poll = sdk.render_task(task.id)
if poll.status == "failure":
print(poll)
raise Exception(f"Render failed for '{look.title}'")
elif poll.status == "success":
break
time.sleep(delay)
elapsed += delay
print(f"Render task completed in {elapsed} seconds")
result = sdk.render_task_results(task.id)
filename = f"{look.title}.{result_format}"
with open(filename, "wb") as f:
f.write(result)
print(f"Look saved to '{filename}'")
look_title = sys.argv[1] if len(sys.argv) > 1 else "Name"
image_width = int(sys.argv[2]) if len(sys.argv) > 2 else 545
image_height = int(sys.argv[3]) if len(sys.argv) > 3 else 842
image_format = sys.argv[4] if len(sys.argv) > 4 else "png"
if not look_title:
raise Exception(
textwrap.dedent(
"""
Please provide: <lookTitle> [<img_width>] [<img_height>] [<img_format>]
img_width defaults to 545
img_height defaults to 842
img_format defaults to 'png'"""
)
)
look = get_look(look_title)
#Dataframe storage
download_look(look, image_format, image_width, image_height)
The SDK function you are using (create_look_render_task), which is described here only allows you to download in either pdf, png, or jpg.
If you want to get the data from a Look into a dataframe then you may want to look into using the run_look function instead described here. When you use run_look you can change the result_format to CSV and then write your own code to convert to a dataframe.
Have a class Header:
class Header:
MAX_FORMAT_LENGTH=8
magicnum = "hide" #str
size = 0
fformat = "txt"
Have a fucntion, which can encode pixel in an image:
def encode_in_pixel(byte, pixel):
"""Encodes a byte in the two least significant bits of each channel.
A 4-channel pixel is needed, which should be a tuple of 4 values from 0 to
255.
"""
r = (byte&3)
g = (byte&12)>>2
b = (byte&48)>>4
a = (byte&192)>>6
color = (r+(pixel[0]&252),\
g+(pixel[1]&252),\
b+(pixel[2]&252),\
a+(pixel[3]&252)) # Here is my problem
return color
After inputting correct arg in command line , while building, I have an error, which says that:
a = pixel[3]&3
IndexError: tuple index out of range
I was trying to input diffiret kinds of images, like: png,jpg,jpeg and etc.
Because wanted to check A 4-channel pixel out because I could wrong with the image. But no, I have the same error.
I would like to show , how my encoding process looks ,except encode_in_pixel(), I have a function ,which call encode_in_pixel:
def encode(image, data, filename, encryption=False, password=""):
im = Image.open(image)
px = im.load()
#Create a header
header = Header()
header.size = len(data)
header.fformat = "" if (len(filename.split(os.extsep))<2)\
else filename.split(os.extsep)[1]
#Add the header to the file data
headerdata = struct.pack("4s"+\
"I"+\
str(Header.MAX_FORMAT_LENGTH)+"s",\
header.magicnum, header.size, header.fformat)
filebytes = headerdata + data
#Optional encryption step
if encrypt:
if password:
filebytes = encrypt(filebytes, password,\
padding=im.width*im.height - len(filebytes))
else:
print "Password is empty, encryption skipped"
#Ensure the image is large enough to hide the data
if len(filebytes) > im.width*im.height:
print "Image too small to encode the file. \
You can store 1 byte per pixel."
exit()
for i in range(len(filebytes)):
coords = (i%im.width, i/im.width)
byte = ord(filebytes[i])
px[coords[0], coords[1]] = encode_in_pixel(byte, px[coords[0], coords[1]])
#here i'm trying to call function , where I have an error
im.save("output.png", "PNG")
I can be mistake in given args, but if it is , how should I give them?
My goal is to read a wave file and edit the data of it by adding a random number to each bit of data in the range of -1 to 1 with the hope of creating some distortion and then saving it as an edited wave file. I read and edit the wave file like so:
riffTag = fileIn.read(4)
if riffTag != 'RIFF':
print 'not a valid RIFF file'
exit(1)
riffLength = struct.unpack('<L', fileIn.read(4))[0]
riffType = fileIn.read(4)
if riffType != 'WAVE':
print 'not a WAV file'
exit(1)
# now read children
while fileIn.tell() < 8 + riffLength:
tag = fileIn.read(4)
length = struct.unpack('<L', fileIn.read(4))[0]
if tag == 'fmt ': # format element
fmtData = fileIn.read(length)
fmt, numChannels, sampleRate, byteRate, blockAlign, bitsPerSample = struct.unpack('<HHLLHH', fmtData)
stHeaderFields['AudioFormat'] = fmt
stHeaderFields['NumChannels'] = numChannels
stHeaderFields['SampleRate'] = sampleRate
stHeaderFields['ByteRate'] = byteRate
stHeaderFields['BlockAlign'] = blockAlign
stHeaderFields['BitsPerSample'] = bitsPerSample
elif tag == 'data': # data element
rawData = fileIn.read(length)
else: # some other element, just skip it
fileIn.seek(length, 1)
numChannels = stHeaderFields['NumChannels']
# some sanity checks
assert(stHeaderFields['BitsPerSample'] == 16)
assert(numChannels * stHeaderFields['BitsPerSample'] == blockAlign * 8)
samples = []
edited_samples = []
for offset in range(0, len(rawData), blockAlign):
samples.append(struct.unpack('<h', rawData[offset:offset+blockAlign]))
for sample in samples:
edited_samples.append(sample[0] + random.randint(-1, 1))
After I've done this I try to save the data is a new edited wave file by doing the following:
foo = []
for sample in edited_samples:
foo.append(struct.pack('<h', int(sample)))
with open(fileIn.name + ' edited.wav', 'w') as file_out:
file_out.write('RIFF')
file_out.write(struct.pack('<L', riffLength))
file_out.write('WAVE')
file_out.write(ur'fmt\u0020')
file_out.write(struct.pack('<H', fmt))
file_out.write(struct.pack('<H', numChannels))
file_out.write(struct.pack('<L', sampleRate))
file_out.write(struct.pack('<L', byteRate))
file_out.write(struct.pack('<H', blockAlign))
file_out.write(struct.pack('<H', bitsPerSample))
file_out.write('data')
for item in foo:
file_out.write(item)
While it doesn't give me any errors I can't play the new wave file in a media player. When I try open my new wave file I get a crash on the line fmt, numChannels, sampleRate, byteRate, blockAlign, bitsPerSample = struct.unpack('<HHLLHH', fmtData) with the error error: unpack requires a string argument of length 16. I imagine I'm building the wave file wrong. How do I build it correctly?
Unless you're intent on writing the support for .wav files yourself for some other reason (getting experience with dealing with binary files, etc.), don't do this. Python comes with the wave module that handles all of the file format issues and lets you just work with the data.
Okay so I've been trying to solve this for about six hours now and it's just not happening.
I've got this function that grabs a bunch of image (GIF) files from a URL based on a timestamp (using the Requests library. The images get saved to my desktop in a specific directory just fine.
When I try to open that image, rename it and process it then everything breaks.
Here's the initial method that sets everything up:
def createImage():
AB_CODES = ["WHK", "WHN", "WWW", "XBU", "XSM"]
BASE_URL = "http://url_where_I_get_images_from"
orig_dir = "originals/"
new_dir = "processed/"
# Add new image for each code
for code in AB_CODES:
radar_dir = BASE_URL + code
url = requests.head(radar_dir)
#parseUrl creates a valid timestamp corresponding to the latest image.
timestamp = parseUrl(url)
filename = timestamp + "_" + code + "_PRECIP_RAIN.gif"
radar = BASE_URL + code + "/" + filename
radar_img = requests.get(radar, timeout=30.000)
# This is where the file from original source gets saved to my desktop, works.
# Image gets saved in path/originals/img.gif
if (radar_img.status_code == requests.codes.ok):
image = radar_img.content
filepath = os.path.join(orig_dir, filename)
imgfile = open(filepath, "wb")
imgfile.write(image)
imgfile.close()
# This is where I create a new image to be saved and worked on in
# path/processed/new_img.gif
image = radar_img.content
filename = code + "_radar.gif"
convpath = os.path.join(new_dir, filename)
convimg = open(convpath, "wb")
convimg.write(image)
# This is the call to the function where I use imagemagick
# which is not working
image = processImage(convimg.name, "processed/XSM_radar_output.gif")
convimg.close()
Here are the two methods that make up my processing function. Right now it's in more of a testing phase because it won't work.
def formatArg(arg):
if arg.startswith("#") or " " in arg:
return repr(arg)
return arg
def processImage(input, output, verbose=True, shell=True):
args = [
"convert", input,
"-resize", "50x50",
output
]
if verbose:
print("Image: %s" % input)
print(" ".join(formatArg(a) for a in args))
print
if os.path.exists(input):
try:
result = subprocess.check_call(args)
except subprocess.CalledProcessError:
result = False
if result:
print("%s : SUCCESS!" % output)
else:
print("%s : FAIL!" % output)
I've tried it without shell=true. The error message I get is that the image is corrupted:
Image: processed/XSM_radar.gif
convert processed/XSM_radar.gif -resize 50x50 processed/XSM_radar.gif
convert.im6: corrupt image `processed/XSM_radar.gif' # error/gif.c/ReadGIFImage/1356.
convert.im6: no images defined `processed/XSM_radar_output.gif' # error/convert.c/ConvertImageCommand/3044.
processed/XSM_radar.gif : FAIL!
I don't understand why it's telling me that it's corrupted. I've run these exact same commands from the command line and it works just fine.
(I have imported subprocess)
Someone helped me determine the error.
def processImage(input, output, verbose=True, shell=True):
args = [
"convert", input,
"-resize", "50x50",
output
]
if verbose:
print("Image: %s" % input)
print(" ".join(formatArg(a) for a in args))
print
if os.path.exists(input):
try:
**result = subprocess.check_call(args)**
**except subprocess.CalledProcessError:**
**result = False**
**if result:**
print("%s : SUCCESS!" % output)
else:
print("%s : FAIL!" % output)
That section with the results should have been
result_code = subprocess.check_call(args)
and if it returned an error, result_code should have been set equal to 1.
So:
if result_code == 0:
do stuff
Thank you for your attention!
Have a lovely day.
Evening,
I am working on a project that requires me to read in multichannel wav files in 32-bit float.
When I read a specific file (1 minute long, 6 channels, 48k fs) in into Matlab and measure it with tic/toc it parses the file in 2.456482 seconds.
Matlab Code for file reading speed measurement
tic
wavread('C:/data/testData/6ch.wav');
toc
When I do it in python (mind you, I'm pretty unfamiliar with python) it takes 18.1655315617 seconds!
It seems to me like the way I am doing it is inefficient (I did get it down to 18 from 28 but it's still too much...)
I stripped the code to what is relevant to this subject:
Python Code for file reading speed measurement
import wave32
import struct
import time
import numpy as np
def getWavData(inFile)
wavFile = wave32.open(inFile, 'r')
wavParams = wavFile.getparams()
nChannels = wavParams[0]
byteDepth = wavParams[1]
nFrames = wavParams[3]
wavData = np.empty([nFrames, nChannels], np.float32)
frames = wavFile.readframes(nFrames)
for i in range(nFrames):
for j in range(nChannels):
start = ( i * nChannels + j ) * byteDepth
stop = start + byteDepth
wavData[i][j] = struct.unpack('<f', frames[start:stop])[0]
return wavData
inFile = 'C:/data/testData/6ch.wav'
start = time.clock()
data2 = getWavData(inFile)
elapsed = time.clock()
elapsedNew = elapsed - start
print str(elapsedNew)
please not that wav32 is a small hack I had to perform on wave.py to enable 32-bit float reading.
"""Stuff to parse WAVE files.
Usage.
Reading WAVE files:
f = wave.open(file, 'r')
where file is either the name of a file or an open file pointer.
The open file pointer must have methods read(), seek(), and close().
When the setpos() and rewind() methods are not used, the seek()
method is not necessary.
This returns an instance of a class with the following public methods:
getnchannels() -- returns number of audio channels (1 for
mono, 2 for stereo)
getsampwidth() -- returns sample width in bytes
getframerate() -- returns sampling frequency
getnframes() -- returns number of audio frames
getcomptype() -- returns compression type ('NONE' for linear samples)
getcompname() -- returns human-readable version of
compression type ('not compressed' linear samples)
getparams() -- returns a tuple consisting of all of the
above in the above order
getmarkers() -- returns None (for compatibility with the
aifc module)
getmark(id) -- raises an error since the mark does not
exist (for compatibility with the aifc module)
readframes(n) -- returns at most n frames of audio
rewind() -- rewind to the beginning of the audio stream
setpos(pos) -- seek to the specified position
tell() -- return the current position
close() -- close the instance (make it unusable)
The position returned by tell() and the position given to setpos()
are compatible and have nothing to do with the actual position in the
file.
The close() method is called automatically when the class instance
is destroyed.
Writing WAVE files:
f = wave.open(file, 'w')
where file is either the name of a file or an open file pointer.
The open file pointer must have methods write(), tell(), seek(), and
close().
This returns an instance of a class with the following public methods:
setnchannels(n) -- set the number of channels
setsampwidth(n) -- set the sample width
setframerate(n) -- set the frame rate
setnframes(n) -- set the number of frames
setcomptype(type, name)
-- set the compression type and the
human-readable compression type
setparams(tuple)
-- set all parameters at once
tell() -- return current position in output file
writeframesraw(data)
-- write audio frames without pathing up the
file header
writeframes(data)
-- write audio frames and patch up the file header
close() -- patch up the file header and close the
output file
You should set the parameters before the first writeframesraw or
writeframes. The total number of frames does not need to be set,
but when it is set to the correct value, the header does not have to
be patched up.
It is best to first set all parameters, perhaps possibly the
compression type, and then write audio frames using writeframesraw.
When all frames have been written, either call writeframes('') or
close() to patch up the sizes in the header.
The close() method is called automatically when the class instance
is destroyed.
"""
import __builtin__
__all__ = ["open", "openfp", "Error"]
class Error(Exception):
pass
WAVE_FORMAT_PCM = 0x0001
WAVE_FORMAT_IEEE_FLOAT = 0x0003
_array_fmts = None, 'b', 'h', None, 'l'
# Determine endian-ness
import struct
if struct.pack("h", 1) == "\000\001":
big_endian = 1
else:
big_endian = 0
from chunk import Chunk
class Wave_read:
"""Variables used in this class:
These variables are available to the user though appropriate
methods of this class:
_file -- the open file with methods read(), close(), and seek()
set through the __init__() method
_nchannels -- the number of audio channels
available through the getnchannels() method
_nframes -- the number of audio frames
available through the getnframes() method
_sampwidth -- the number of bytes per audio sample
available through the getsampwidth() method
_framerate -- the sampling frequency
available through the getframerate() method
_comptype -- the AIFF-C compression type ('NONE' if AIFF)
available through the getcomptype() method
_compname -- the human-readable AIFF-C compression type
available through the getcomptype() method
_soundpos -- the position in the audio stream
available through the tell() method, set through the
setpos() method
These variables are used internally only:
_fmt_chunk_read -- 1 iff the FMT chunk has been read
_data_seek_needed -- 1 iff positioned correctly in audio
file for readframes()
_data_chunk -- instantiation of a chunk class for the DATA chunk
_framesize -- size of one frame in the file
"""
def initfp(self, file):
self._convert = None
self._soundpos = 0
self._file = Chunk(file, bigendian = 0)
if self._file.getname() != 'RIFF':
raise Error, 'file does not start with RIFF id'
if self._file.read(4) != 'WAVE':
raise Error, 'not a WAVE file'
self._fmt_chunk_read = 0
self._data_chunk = None
while 1:
self._data_seek_needed = 1
try:
chunk = Chunk(self._file, bigendian = 0)
except EOFError:
break
chunkname = chunk.getname()
if chunkname == 'fmt ':
self._read_fmt_chunk(chunk)
self._fmt_chunk_read = 1
elif chunkname == 'data':
if not self._fmt_chunk_read:
raise Error, 'data chunk before fmt chunk'
self._data_chunk = chunk
self._nframes = chunk.chunksize // self._framesize
self._data_seek_needed = 0
break
chunk.skip()
if not self._fmt_chunk_read or not self._data_chunk:
raise Error, 'fmt chunk and/or data chunk missing'
def __init__(self, f):
self._i_opened_the_file = None
if isinstance(f, basestring):
f = __builtin__.open(f, 'rb')
self._i_opened_the_file = f
# else, assume it is an open file object already
try:
self.initfp(f)
except:
if self._i_opened_the_file:
f.close()
raise
def __del__(self):
self.close()
#
# User visible methods.
#
def getfp(self):
return self._file
def rewind(self):
self._data_seek_needed = 1
self._soundpos = 0
def close(self):
if self._i_opened_the_file:
self._i_opened_the_file.close()
self._i_opened_the_file = None
self._file = None
def tell(self):
return self._soundpos
def getnchannels(self):
return self._nchannels
def getnframes(self):
return self._nframes
def getsampwidth(self):
return self._sampwidth
def getframerate(self):
return self._framerate
def getcomptype(self):
return self._comptype
def getcompname(self):
return self._compname
def getparams(self):
return self.getnchannels(), self.getsampwidth(), \
self.getframerate(), self.getnframes(), \
self.getcomptype(), self.getcompname()
def getmarkers(self):
return None
def getmark(self, id):
raise Error, 'no marks'
def setpos(self, pos):
if pos < 0 or pos > self._nframes:
raise Error, 'position not in range'
self._soundpos = pos
self._data_seek_needed = 1
def readframes(self, nframes):
if self._data_seek_needed:
self._data_chunk.seek(0, 0)
pos = self._soundpos * self._framesize
if pos:
self._data_chunk.seek(pos, 0)
self._data_seek_needed = 0
if nframes == 0:
return ''
if self._sampwidth > 1 and big_endian:
# unfortunately the fromfile() method does not take
# something that only looks like a file object, so
# we have to reach into the innards of the chunk object
import array
chunk = self._data_chunk
data = array.array(_array_fmts[self._sampwidth])
nitems = nframes * self._nchannels
if nitems * self._sampwidth > chunk.chunksize - chunk.size_read:
nitems = (chunk.chunksize - chunk.size_read) / self._sampwidth
data.fromfile(chunk.file.file, nitems)
# "tell" data chunk how much was read
chunk.size_read = chunk.size_read + nitems * self._sampwidth
# do the same for the outermost chunk
chunk = chunk.file
chunk.size_read = chunk.size_read + nitems * self._sampwidth
data.byteswap()
data = data.tostring()
else:
data = self._data_chunk.read(nframes * self._framesize)
if self._convert and data:
data = self._convert(data)
self._soundpos = self._soundpos + len(data) // (self._nchannels * self._sampwidth)
return data
#
# Internal methods.
#
def _read_fmt_chunk(self, chunk):
wFormatTag, self._nchannels, self._framerate, dwAvgBytesPerSec, wBlockAlign = struct.unpack('<hhllh', chunk.read(14))
if wFormatTag == WAVE_FORMAT_PCM or wFormatTag==WAVE_FORMAT_IEEE_FLOAT:
sampwidth = struct.unpack('<h', chunk.read(2))[0]
self._sampwidth = (sampwidth + 7) // 8
else:
#sampwidth = struct.unpack('<h', chunk.read(2))[0]
#self._sampwidth = (sampwidth + 7) // 8
raise Error, 'unknown format: %r' % (wFormatTag,)
self._framesize = self._nchannels * self._sampwidth
self._comptype = 'NONE'
self._compname = 'not compressed'
class Wave_write:
"""Variables used in this class:
These variables are user settable through appropriate methods
of this class:
_file -- the open file with methods write(), close(), tell(), seek()
set through the __init__() method
_comptype -- the AIFF-C compression type ('NONE' in AIFF)
set through the setcomptype() or setparams() method
_compname -- the human-readable AIFF-C compression type
set through the setcomptype() or setparams() method
_nchannels -- the number of audio channels
set through the setnchannels() or setparams() method
_sampwidth -- the number of bytes per audio sample
set through the setsampwidth() or setparams() method
_framerate -- the sampling frequency
set through the setframerate() or setparams() method
_nframes -- the number of audio frames written to the header
set through the setnframes() or setparams() method
These variables are used internally only:
_datalength -- the size of the audio samples written to the header
_nframeswritten -- the number of frames actually written
_datawritten -- the size of the audio samples actually written
"""
def __init__(self, f):
self._i_opened_the_file = None
if isinstance(f, basestring):
f = __builtin__.open(f, 'wb')
self._i_opened_the_file = f
try:
self.initfp(f)
except:
if self._i_opened_the_file:
f.close()
raise
def initfp(self, file):
self._file = file
self._convert = None
self._nchannels = 0
self._sampwidth = 0
self._framerate = 0
self._nframes = 0
self._nframeswritten = 0
self._datawritten = 0
self._datalength = 0
self._headerwritten = False
def __del__(self):
self.close()
#
# User visible methods.
#
def setnchannels(self, nchannels):
if self._datawritten:
raise Error, 'cannot change parameters after starting to write'
if nchannels < 1:
raise Error, 'bad # of channels'
self._nchannels = nchannels
def getnchannels(self):
if not self._nchannels:
raise Error, 'number of channels not set'
return self._nchannels
def setsampwidth(self, sampwidth):
if self._datawritten:
raise Error, 'cannot change parameters after starting to write'
if sampwidth < 1 or sampwidth > 4:
raise Error, 'bad sample width'
self._sampwidth = sampwidth
def getsampwidth(self):
if not self._sampwidth:
raise Error, 'sample width not set'
return self._sampwidth
def setframerate(self, framerate):
if self._datawritten:
raise Error, 'cannot change parameters after starting to write'
if framerate <= 0:
raise Error, 'bad frame rate'
self._framerate = framerate
def getframerate(self):
if not self._framerate:
raise Error, 'frame rate not set'
return self._framerate
def setnframes(self, nframes):
if self._datawritten:
raise Error, 'cannot change parameters after starting to write'
self._nframes = nframes
def getnframes(self):
return self._nframeswritten
def setcomptype(self, comptype, compname):
if self._datawritten:
raise Error, 'cannot change parameters after starting to write'
if comptype not in ('NONE',):
raise Error, 'unsupported compression type'
self._comptype = comptype
self._compname = compname
def getcomptype(self):
return self._comptype
def getcompname(self):
return self._compname
def setparams(self, params):
nchannels, sampwidth, framerate, nframes, comptype, compname = params
if self._datawritten:
raise Error, 'cannot change parameters after starting to write'
self.setnchannels(nchannels)
self.setsampwidth(sampwidth)
self.setframerate(framerate)
self.setnframes(nframes)
self.setcomptype(comptype, compname)
def getparams(self):
if not self._nchannels or not self._sampwidth or not self._framerate:
raise Error, 'not all parameters set'
return self._nchannels, self._sampwidth, self._framerate, \
self._nframes, self._comptype, self._compname
def setmark(self, id, pos, name):
raise Error, 'setmark() not supported'
def getmark(self, id):
raise Error, 'no marks'
def getmarkers(self):
return None
def tell(self):
return self._nframeswritten
def writeframesraw(self, data):
self._ensure_header_written(len(data))
nframes = len(data) // (self._sampwidth * self._nchannels)
if self._convert:
data = self._convert(data)
if self._sampwidth > 1 and big_endian:
import array
data = array.array(_array_fmts[self._sampwidth], data)
data.byteswap()
data.tofile(self._file)
self._datawritten = self._datawritten + len(data) * self._sampwidth
else:
self._file.write(data)
self._datawritten = self._datawritten + len(data)
self._nframeswritten = self._nframeswritten + nframes
def writeframes(self, data):
self.writeframesraw(data)
if self._datalength != self._datawritten:
self._patchheader()
def close(self):
if self._file:
self._ensure_header_written(0)
if self._datalength != self._datawritten:
self._patchheader()
self._file.flush()
self._file = None
if self._i_opened_the_file:
self._i_opened_the_file.close()
self._i_opened_the_file = None
#
# Internal methods.
#
def _ensure_header_written(self, datasize):
if not self._headerwritten:
if not self._nchannels:
raise Error, '# channels not specified'
if not self._sampwidth:
raise Error, 'sample width not specified'
if not self._framerate:
raise Error, 'sampling rate not specified'
self._write_header(datasize)
def _write_header(self, initlength):
assert not self._headerwritten
self._file.write('RIFF')
if not self._nframes:
self._nframes = initlength / (self._nchannels * self._sampwidth)
self._datalength = self._nframes * self._nchannels * self._sampwidth
self._form_length_pos = self._file.tell()
self._file.write(struct.pack('<l4s4slhhllhh4s',
36 + self._datalength, 'WAVE', 'fmt ', 16,
WAVE_FORMAT_PCM, self._nchannels, self._framerate,
self._nchannels * self._framerate * self._sampwidth,
self._nchannels * self._sampwidth,
self._sampwidth * 8, 'data'))
self._data_length_pos = self._file.tell()
self._file.write(struct.pack('<l', self._datalength))
self._headerwritten = True
def _patchheader(self):
assert self._headerwritten
if self._datawritten == self._datalength:
return
curpos = self._file.tell()
self._file.seek(self._form_length_pos, 0)
self._file.write(struct.pack('<l', 36 + self._datawritten))
self._file.seek(self._data_length_pos, 0)
self._file.write(struct.pack('<l', self._datawritten))
self._file.seek(curpos, 0)
self._datalength = self._datawritten
def open(f, mode=None):
if mode is None:
if hasattr(f, 'mode'):
mode = f.mode
else:
mode = 'rb'
if mode in ('r', 'rb'):
return Wave_read(f)
elif mode in ('w', 'wb'):
return Wave_write(f)
else:
raise Error, "mode must be 'r', 'rb', 'w', or 'wb'"
openfp = open # B/W compatibility
Sorry for the long code BTW :)
So my question is: is the wave.py module inherently slow (any alternatives to fix this?) or am I doing something inefficient?
I suppose I could just read in the wav header with a custom function and read the file in in a different way, but it seems like this is going to be A LOT of work, especially since I don't know a lot about 1) python and 2) file handling
Kind regards,
K.
Edit: I tried unutbu's suggestion but that does not work as scipy does not accept >16 bit.
When I try to parse the wav file through the scipy wavreader I get this message:
C:\Users\King Broos\AppData\Local\Enthought\Canopy32\System\lib\site-packages\scipy\io\wavfile.py:31: WavFileWarning: Unfamiliar format bytes
warnings.warn("Unfamiliar format bytes", WavFileWarning)
C:\Users\King Broos\AppData\Local\Enthought\Canopy32\System\lib\site-packages\scipy\io\wavfile.py:121: WavFileWarning: chunk not understood
warnings.warn("chunk not understood", WavFileWarning)
Looking into the code of wavfile.py this is the line where it throws the exception:
if (comp != 1 or size > 16):
warnings.warn("Unfamiliar format bytes", WavFileWarning)
I really need either 24 or 32 bit so I guess scipy not an option?
If you can install or have scipy, then use wavfile.read:
import scipy.io.wavfile as wavfile
sample_rate, x = wavfile.read(filename)
You might also want to study the source code, here.
Note that scipy.io.wavfile does not use Python's wave module. I'm not sure if it reads your IEEE_FLOAT format or not, but it does not do the same check as wave.py:
if wFormatTag == WAVE_FORMAT_PCM or wFormatTag==WAVE_FORMAT_IEEE_FLOAT:
sampwidth = struct.unpack('<h', chunk.read(2))[0]
self._sampwidth = (sampwidth + 7) // 8
else:
#sampwidth = struct.unpack('<h', chunk.read(2))[0]
#self._sampwidth = (sampwidth + 7) // 8
raise Error, 'unknown format: %r' % (wFormatTag,)
so perhaps it will work out-of-the-box.
By the way, instead of making your own module, wave32.py which is almost exactly the same as wave.py from the standard library, you could use monkey-patching:
import wave
import struct
WAVE_FORMAT_IEEE_FLOAT = 0x0003
def _read_fmt_chunk(self, chunk):
wFormatTag, self._nchannels, self._framerate, dwAvgBytesPerSec, wBlockAlign = struct.unpack('<hhllh', chunk.read(14))
if wFormatTag == WAVE_FORMAT_PCM or wFormatTag == WAVE_FORMAT_IEEE_FLOAT:
sampwidth = struct.unpack('<h', chunk.read(2))[0]
self._sampwidth = (sampwidth + 7) // 8
else:
raise Error, 'unknown format: %r' % (wFormatTag,)
self._framesize = self._nchannels * self._sampwidth
self._comptype = 'NONE'
self._compname = 'not compressed'
wave.Wave_read._read_fmt_chunk = _read_fmt_chunk
You can also use numpy directly:
import numpy as np
fs = np.fromfile(filename, dtype=np.int32, count=1, offset=24)[0] # Hz
byte_length = np.fromfile(filename, dtype=np.int32, count=1, offset=40)[0]
To manually read pieces of metadata. I recommend using a hex editor and wave format reference to verify the locations for pieces of metadata and the offset to the start of the data chunk (might not be 40 or 44 bytes in).
To read 32-bit WAVE_FORMAT_IEEE_FLOAT:
data = np.fromfile(filename, dtype=np.float32, count=byte_length // 4, offset=44)
To read 24-bit WAVE_FORMAT_PCM:
# prepend zero-byte to each sample (since there's no np.int24)
# then flatten, convert normally and byte-shift to correct for extra byte
data = np.zeros([byte_length // 3, 4], dtype=np.int8)
data[:, 1:] = np.fromfile(filename, dtype=np.int8, count=byte_length, offset=44).reshape(-1, 3)
data = np.right_shift(data.reshape(-1).view(dtype=np.int32), 8)
data = data / 2 ** 23 # if you want to normalize
Depends on the wavefile and machine, but this seems to be ~120 times faster than a loop for a 4.4 MB 24-bit .wav file, but there's likely bigger performance gains for bigger files (until swap is required, I think there's ~5 memory copies performed, including normalization).
This assumes:
No extra chunks at the start of the file, else offset= parameters are wrong
Single channel - reshape the array and/or change the byte order for multi-channel, with something like .reshape(num_channels, -1, order='F')
Little-endian I think